Student Privacy
Block or flag requests when student PII is detected. Education and student privacy controls. Apply the Student Privacy pack, test with examples, and view contextual audit events.
Portal
Dashboard → Deployments — Open a deployment. Go to the Policies tab. Scroll to Enforcement packs. Find Student Privacy and click Apply.
What it detects
- Student identifier — Name + ID pattern (e.g. "Student Emma Svensson, ID 123456")
- Personnummer — Swedish national ID format
- Email — Email addresses
- Phone — Phone numbers
- Long numeric IDs — 6–12 digit identifiers
Rules
- Student identifier detected → Block or flag (configurable)
- Multiple PII signals → Block
- Weak PII only (email, phone) → Flag
Test it
In the deployment detail page, use the Try it section in the Policies tab.
Blocked — student name + ID
Use this input to trigger a block:
{"prompt": "Student Emma Svensson, ID 123456, needs help with math"}Expected: Blocked. Request never reaches the model. Violations show CONTEXTUAL_BLOCK.
Allowed — no PII
{"prompt": "How do I create a lesson plan for grade 6?"}Expected: Allowed (passed policy).
Flagged — email only
{"prompt": "Contact student at emma@example.com"}Expected: Flagged (or blocked depending on config). Request may still be allowed but logged for audit.
Readiness, not legal compliance
Quantlix provides runtime policy enforcement and exportable evidence on supported production paths to help teams build EU AI Act readiness and broader AI governance workflows. It is not legal advice, a conformity assessment, CE marking, or a guarantee of regulatory compliance. Risk classification, DPIAs, and legal interpretation remain your responsibility.
Audit
Deployment → Audit tab. Filter by Blocked. Events show contextual with policy_pack, detection_types, and reason_codes. No raw sensitive text is logged.
Apply via API
curl -X POST https://api.quantlix.ai//deployments/DEPLOYMENT_ID/apply-pack \
-H "X-API-Key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"pack_id": "student-privacy"}'